TT's mapred-site.xml

mapred-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>

  <property>
    <name>mapred.job.tracker</name>
    <value>REDACTED (an ec2 internal DNS name):8021</value>
    <final>true</final>
  </property>

  <property>
    <name>mapred.local.dir</name>
    <value>/mnt/data/hadoop/mapred/local</value>
    <final>true</final>
  </property>

  <property>
    <name>mapred.system.dir</name>
    <value>/mapreduce/system</value>
    <final>true</final>
  </property>

  <property>
    <name>mapred.jobtracker.taskScheduler</name>
    <value>org.apache.hadoop.mapred.FairScheduler</value>
    <final>true</final>
  </property>

  <property>
    <name>mapred.child.java.opts</name>
    <value>-Xmx1024m</value>
    <final>true</final>
  </property>

  <property>
    <name>mapred.child.ulimit</name>
    <value>2097000</value>
    <final>true</final>
  </property>

  <property>
    <name>mapred.tasktracker.map.tasks.maximum</name>
    <value>1</value>
    <final>true</final>
  </property>
  <property>
    <name>mapred.tasktracker.reduce.tasks.maximum</name>
    <value>1</value>
    <final>true</final>
  </property>

  <property>
    <name>mapred.compress.map.output</name>
    <value>true</value>
  </property>
  
  <property>
    <name>mapred.map.output.compression.codec</name>
    <value>com.hadoop.compression.lzo.LzoCodec</value>
  </property>
  
  <property>
    <name>io.sort.factor</name>
    <value>50</value>
  </property>

  <property>
    <name>io.sort.mb</name>
    <value>200</value>
  </property>

  <property>
    <name>mapred.reduce.max.attempts</name>
    <value>2</value>
    <final>true</final>
  </property>

</configuration>